© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 63254
    Prev
    Next
    INDEX
    Explanations

    references to financial statistics or budget-related terms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Auckland
    -0.09
     Maharashtra
    -0.09
     Arizona
    -0.08
    izona
    -0.08
     Chicago
    -0.08
    uckland
    -0.08
     Tucson
    -0.07
     Detroit
    -0.07
    Chicago
    -0.07
     Ark
    -0.07
    POSITIVE LOGITS
     Virginia
    0.18
    Virginia
    0.17
     Vienna
    0.13
     Charlottesville
    0.13
     Maryland
    0.13
     Norfolk
    0.12
     RVA
    0.12
     Fairfax
    0.12
     Richmond
    0.11
     VA
    0.10
    Activations Density 0.123%

    No Known Activations